© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 184
    Prev
    Next
    INDEX
    Explanations

    words following common suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ign
    0.74
     meaningfully
    0.74
     inv
    0.74
     unpredictable
    0.72
    ,
    0.72
     of
    0.70
     auditory
    0.70
     truthfully
    0.70
     hostile
    0.69
     upper
    0.68
    POSITIVE LOGITS
    Gambar
    1.33
    এর
    1.22
    Enh
    1.18
    എ
    1.17
    Makanan
    1.16
    Z
    1.16
     специальные
    1.15
    H
    1.15
    Ț
    1.12
    Tidak
    1.10
    Activations Density 1.076%

    No Known Activations